Neural network model for predictive mapping of endogenous gold deposits

The scientific article is devoted to the development of a neural network for modeling the heterogeneous distribution of mineralization in the gold ore complex at the stage of exploration and development of the deposit. In numerous works on the implementation and use of artificial neural networks, methods and models adapted for the stage of regional (small-scale) mapping are proposed in order to predict and evaluate large areas with a high degree of mineralization. These models and methods described in the literature on this topic are not suitable for predictive mapping of new promising local zones in order to expand the exploited field, in the sense that the definition of classes of mineral prospectivity levels depends not only on the spatial parameters (geographical location) of the targets, but also on other parameters, such as the values of mineralization intensity (e.g., geochemical content of the mineral) at each point of the target, the threshold value of mineralization, etc. An analysis of existing methods for predictive mapping of mineral prospects was carried out. The task of implementing a neural network architecture is formulated. The following research methods were used in the work: modeling the heterogeneous distribution of mineralization using spatial autocorrelation. (dependent parameter); factors influencing the heterogeneity of mineralization (independent parameters) were identified and selected; a neural network (ANN) architecture has been implemented. The article presents the results of the neural network model at the experimental stage for predictive mapping of mineral prospects at the Agbau gold complex, located in the Birimians formations of Paleoproterozoic age in West Africa.

Nkrumah A. H. M., Silina T.S., Faizrakhmanov R.A. Neural network model for predictive mapping of endogenous gold deposits. MIAB. Mining Inf. Anal. Bull. 2025;(1-1): 178-192. [In Russ]. DOI: 10.25018/0236_1493_2025_11_0_178.

Nkrumah Assoumou Herve Mathieu¹, Graduate Student, e-mail: nkvetcho@gmail.com,
T.S. Silina, Cand. Sci. (Geol. Mineral.), Assistant Professor, Ural State Mining University, 620144, Ekaterinburg, Russia, e-mail: tamarasil @mail.ru,
R.A. Faizrakhmanov¹, Dr. Sci. (Econ.), Professor, Head of Chair, e-mail: Fayzrakhmanov@gmail.com,
¹ Perm National Research Polytechnic University, 614990, Perm, Russia.

T.S. Silina, e-mail: tamarasil @mail.ru.

1. Nekrasov E. M. Principles governing the selection of ore regions for gold deposit search. Proceedings of higher educational establishments. Geology and Exploration. 2022, no. 63(6), pp. 77—86. [In Russ]. DOI: 10.32454/0016-7762-2020-63-6-77-86.

2. Minbaleev A. V., Berestnev M. A., Evsikov K. S. Regulating the use of artificial intelligence in the mining industry. News of the Tula state university. Sciences of Earth. 2022, no. 2, pp. 509—525. [In Russ]. DOI: 10.46689/2218-5194-2022-2-1-509-525.

3. Potekhin D. V., Galkin S. V. Application of machine learning technology in modeling lithotype distribution in the Permo-Carboniferous oil deposit of the Usinskoye field. Journal of Mining Institute. 2023, vol. 259, pp. 41—51. [In Russ]. DOI: 10.31897/PMI.2022.101.

4. Maiorov K. N., Kalashnikov М. Т. Application of machine learning algorithms for solving problems in the oil and gas sector. Intelligent systems in manufacturing. 2021, no. 3, pp. 55 — 64. [In Russ]. DOI: 10.22213/2410-9304-2021-3-55-64.

5. Rylnikova M. V., Klebanov D. A., Makeev M. A., Kadochnikov M. V. Application of artificial intelligence and the future of big data analytics in the mining industry. Russian Mining Industry Journal. 2022, no. 3, pp. 89—92. [In Russ]. DOI: 10.30686/1609-9192-2022-3-89-92.

6. Ghezelbash R., Maghsoudi A., Carranza E. J. M. Optimization of geochemical anomaly detection using a novel genetic K-means clustering (GKMC) algorithm. Computers & Geosciences. 2020, vol. 134, article 104335. DOI: 10.1016/j.cageo.2019.104335.

7. Shirmard H., Farahbakhsh E., Müller R. D., Chandra R. A review of machine learning in processing remote sensing data for mineral exploration. Remote Sensing of Environment. 2022, vol. 268, article 112750. DOI: 10.1016/j.rse.2021.112750.

8. Shaibakov R. A. Using a neural network device to identify the boundaries of geological objects. Tekhnicheskie nauki: traditsii i innovatsii. Sbornik nauchnykh trudov mezhdunarodnoy nauchnoy konferentsii [Technical sciences: Traditions and innovations. Collection of scientific papers of the international scientific conference], Chelyabinsk, 2012, pp. 8—11. [In Russ].

9. Valiev N. G., Propp V. D., Kolesnikov А. А., Berkovich В. H. Improving the technology of underground mining of polymetallic ores at the Korbalikhinsky mine of Sibir-Polymetals JSC. Minerals and Mining Engineering. 2022, no. 2, pp. 36—47. [In Russ].

10. Ghezelbash R., Maghsoudi A., Carranza E. J. Sensitivity analysis of prospectivity modeling to evidence maps: Enhancing success of targeting for epithermal gold, Takab district, NW Iran. Ore Geology Reviews. 2020, vol. 120, article 103394. DOI: 10.1016/j.cageo.2019.104335.

11. Daviran M., Maghsoudi A., Ghezelbash R., Pradhan B. A new strategy for spatial predictive mapping of mineral prospectivity: Automated hyperparameter tuning of random forest approach. Computers & Geosciences. 2021, vol. 148, article 104688. DOI: 10.1016/j.cageo.2021.104688.

12. Rigol-Sanchez J. P., Chica-Olmo M., Abarca-Hernandez F. Artificial neural networks as a tool for mineral potential mapping with GIS. International Journal of Remote Sensing. 2003, vol. 24, no. 5, pp. 1151—1156. DOI: 10.1080/0143116021000031791.

13. Krasnykh S. S. Spatial autocorrelation model of the introduction of digital technologies into the business of the Russian Federation. Bulletin of the Academy of Knowledge. 2020, no. 4 (39), pp. 228—235. [In Russ]. DOI: 10.24411/2304-6139-2020-10467.

14. Shaw K. O., Goïta K., Germain M. Prospectivity mapping of heavy mineral ore deposits based upon machine-learning algorithms: Columbite-tantalite deposits in West-Central Côte d’Ivoire. Minerals. 2022, vol. 12, no. 11, article 1453. DOI: 10.3390/min12111453.

15. Osadebey M., Pedersen M., Arnold D., Wendel-Mitoraj K. Local indicators of spatial autocorrelation (LISA): Application to blind noise-based perceptual quality metric index for magnetic resonance images. Journal of Imaging. 2019, vol. 5, no. 1, article 20. DOI: 10.3390/jimaging5010020.

16. Osovsky S. Neyronnye seti dlya obrabotki informatsii. Per. s pol'skogo I.D. Rudinskogo [Neural networks for information processing. Transl. from Polish Rudinsky I. D.], Moscow, Finansy i statistika, 2002, 344 p.

17. Portance K., Elysée K., Sow L., Marie L. Cartographie géotechnique par deep learning — Approche par réseaux de neurones artificiels. European Scientific Journal. 2019, vol. 15, pp. 233—251. DOI: 10.19044/esj.2019.v15n12p233.

18. Allou G., Boya T. K., Inza C., Eric B., Yacouba C. Etude metallogenique du prospect aurifere de Aoulo-Aoulo (Zone D’afema, sud est de la Cote d’Ivore). European Scientific Journal. 2022, vol. 8. DOI: 10.19044/esipreprint.8. 2022.p313.

19. Gougali F., Kotel’nikov AE., The features of the placement of gold deposits in Algeria. News of the Ural State Mining University. 2023, no. 3(71), pp. 32—39. [In Russ]. DOI: 10.21440/2307-20912023-3-32-39.

20. Ouedraogo B., Sié P., Issan K. Apport de la télédétection et des SIG à l’exploration d’un site aurifère : cas de Dodougou au Burkina Faso. Revue Burkinabè de la Recherche. 2020, vol. 39, pp. 71—84.

21. Pak U. S., Pak C. U. Detection of hydrothermal alteration zones using Landsat 8 OLI image: A case study of gold prospecting in Nyongwon Area, DPR Korea. Journal of the Indian Society of Remote Sensing. 2021, vol. 49, no. 9, pp. 2249—2259. DOI: 10.1007/s12524-021-01385-8.

22. El-Desoky H. M., Tende A. W., Abdel-Rahman A. M., Ene A., Awad H. A., Fahmy W., ElAwny H., Zakaly H. M. H. Hydrothermal alteration mapping using Landsat 8 and ASTER Data and geochemical characteristics of precambrian rocks in the Egyptian shield: A case study from Abu Ghalaga, Southeastern Desert, Egypt. Remote Sensing. 2022, vol. 14, no. 14, article 3456. DOI: 10.3390/ rs14143456.